Brush-less DC motors with permanent magnets are widely used in robotics, electric vehicles, and other industrial applications. Enhancing the performance of a BLDC motor can indeed be challenging due to the presence of...
详细信息
One of the primary objectives of truss structure design optimization is to minimize the total weight by determining the optimal sizes of the truss members while ensuring structural stability and integrity against exte...
详细信息
One of the primary objectives of truss structure design optimization is to minimize the total weight by determining the optimal sizes of the truss members while ensuring structural stability and integrity against external loads. Trusses consist of pin joints connected by straight members, analogous to vertices and edges in a mathematical graph. This characteristic motivates the idea of representing truss joints and members as graph vertices and edges. In this study, a Graph Neural Network (GNN) is employed to exploit the benefits of graph representation and develop a GNN-based surrogate model integrated with a particleswarmoptimization (PSO) algorithm to approximate nodal displacements of trusses during the design optimization process. This approach enables the determination of the optimal cross-sectional areas of the truss members with fewer finite element model (FEM) analyses. The validity and effectiveness of the GNN-based optimization technique are assessed by comparing its results with those of a conventional FEM-based design optimization of three truss structures: a 10-bar planar truss, a 72-bar space truss, and a 200-bar planar truss. The results demonstrate the superiority of the GNN-based optimization, which can achieve the optimal solutions without violating constraints and at a faster rate, particularly for complex truss structures like the 200-bar planar truss problem.
In the present study, artificial neural network (ANN) along with heuristic algorithms, namely particleswarmoptimization (PSO) and simulated annealing (SA), has been employed to carry out the modeling and optimizatio...
详细信息
In the present study, artificial neural network (ANN) along with heuristic algorithms, namely particleswarmoptimization (PSO) and simulated annealing (SA), has been employed to carry out the modeling and optimization procedure of electrical discharge machining (EDM) process on AISI2312 hot worked steel parts. Surface roughness (SR), tool wear rate (TWR) and material removal rate (MRR) are the process quality measures considered as process output characteristics. Determination of a process variables (pulse on and off time, current, voltage and duty factor) combination to minimize TWR and SR and maximize MRR independently (as single objective) and also simultaneously (as multi-criteria) optimization is the main objective of this study. The experimental data are gathered using Taguchi L-36 orthogonal array based on design of experiments approach. Next, the output measures are used to develop the ANN model. Furthermore, the architecture of the ANN has been modified using PSO algorithm. At the last step, in order to determine the best set of process output variables values for a desired set of process quality measures, the developed ANN model is embedded into proposed heuristic algorithms (SA and PSO) with which their derived results have been compared. It is evident that the proposed optimization procedure is quite efficient in modeling (with less than 1% error) and optimization (less than 4 and 7 percent error for single- and multi-objective optimizations, respectively) of EDM process variables.
This article describes a color quantization algorithm that combines two swarm-based methods: particleswarmoptimization and artificial ants. The proposed method is based on a previous method that solves the quantizat...
详细信息
This article describes a color quantization algorithm that combines two swarm-based methods: particleswarmoptimization and artificial ants. The proposed method is based on a previous method that solves the quantization problem by combining the particle swarm optimization algorithm with the K-means algorithm. K-means is a popular clustering method that has been applied to solve a variety of problems, including the color quantization problem. Nevertheless, it is a time-consuming method, which makes combining the particle swarm optimization algorithm and K-means less suitable than other color quantization techniques. The proposed method, however, discards the K-means algorithm and applies the Ant-tree for color quantization algorithm in order to reduce execution time. This article shows that the new method outperforms the original one, since it requires less time to obtain higher quality images. In addition, the images produced are also of better quality than those produced by other well-known color quantization methods, such as Neuquant, Octree, Median-cut, Variance-based, Binary splitting and Wu's methods.
In recent years, the development of software-defined networking (SDN) and network function virtualization (NFV) has provided greater flexibility and programmability for network services. As a novel network architectur...
详细信息
ISBN:
(纸本)9798331532109;9798331532093
In recent years, the development of software-defined networking (SDN) and network function virtualization (NFV) has provided greater flexibility and programmability for network services. As a novel network architecture, Service Function Chaining (SFC) offers operators more possibilities in deploying and managing network service functions. However, current research often overlooks user Quality of Service (QoS) requirements, focusing primarily on operator interests. This paper addresses this gap by proposing a novel approach that integrates multidimensional QoS parameters and combines Simulated Annealing (SA) and particleswarmoptimization (PSO) algorithms to optimize QoS service management in SDN/NFV environments. Specifically, we devise a hybrid optimization strategy based on SA and PSO to achieve efficient resource allocation and service chain scheduling, aiming to enhance the overall QoS experience for users. Experimental results demonstrate significant improvements in network service delivery efficiency and user satisfaction, validating the effectiveness and practicality of the proposed approach.
To address the issue of selfish behavior demonstrated by autonomous vehicles in vehicle-infrastructure cooperation, where vehicles having spare computing resources are disinclined to share them, we propose a vehicle s...
详细信息
ISBN:
(纸本)9798350352900;9798350352894
To address the issue of selfish behavior demonstrated by autonomous vehicles in vehicle-infrastructure cooperation, where vehicles having spare computing resources are disinclined to share them, we propose a vehicle selection-assisted computing scheme based on a credit value incentive mechanism. This scheme is aimed at resolving the reluctance of autonomous vehicles to supply their spare computing resources while also facilitating low-performance vehicles to participate effectively in task computing. Additionally, considering the optimization problem of delay and energy consumption during offloading and computing tasks for autonomous vehicles, we formulate a mathematical problem that integrates weighted sums of delay and energy consumption. To handle this problem, we propose a double populations adaptive particle swarm optimization algorithm (DPAPSO) based on the traditional particle swarm optimization algorithm (PSO). The DPAPSO forms two populations of particles in accordance with our model and utilizes different updating strategies for each population. Experimental results show that the proposed DPAPSO outperforms the traditional particle swarm optimization algorithm in terms of optimization effects within this model. Furthermore, it presents superior performance and stability compared to both the simulated annealing algorithm (SA) and the genetic algorithm (GA).
Space robots have been considered as vehicles for the assembly of large spacecraft. Multi-robots offer the advantage of transporting the modular structure to the target position. This paper investigates the dynamics o...
详细信息
ISBN:
(纸本)9798350360875;9798350360868
Space robots have been considered as vehicles for the assembly of large spacecraft. Multi-robots offer the advantage of transporting the modular structure to the target position. This paper investigates the dynamics of a multi-robot connected to a flexible structure rigidly by manipulators, along with the optimization of end-effector placement on the flexible structure. The assumed mode method is employed to describe the vibration of the flexible structure, while the dynamics are modeled using the Kane method. A comprehensive performance index is proposed based on the model, incorporating energy consumption and vibration amplitude. The placement of end-effectors is optimized using the particleswarmoptimization (PSO) algorithm. Various cases involving two transportation directions and two magnitudes of vibration amplitude metrics are investigated. Numerical simulations are conducted to demonstrate the feasibility of the optimized placement.
The load profile can reflect the change of the grid load over time. By connecting electric vehicles to the grid for charging and discharging, the goal of peak shaving and valley filling is realized, thus flattening th...
详细信息
ISBN:
(纸本)9798350387780;9798350387797
The load profile can reflect the change of the grid load over time. By connecting electric vehicles to the grid for charging and discharging, the goal of peak shaving and valley filling is realized, thus flattening the load profile and improving the stability of grid operation. Aiming at this characteristic, a method for optimal scheduling of electric vehicle charging based on an improved particleswarmalgorithm is proposed in this paper. First, the proposed method constructs the electric vehicle charging scenario by Monte Carlo. Then, the improved particleswarmalgorithm is used to solve the optimal charging and discharging quantity of electric vehicles in each period to minimize the load variance. By comparing the improved particleswarmalgorithm with other intelligent algorithms on the benchmark function test set, the improved particleswarmalgorithm is verified that it has superiority in convergence ability and optimization accuracy. Simulation results show that the scheduling of electric vehicle charging using the improved particleswarmalgorithm reduces the peak valley difference of the power grid by 6.31% and the load variance by 74432kW(2) compared with the classical particleswarmalgorithm.
The trajectory optimization problem of cooperative six-axis robot based on time optimization is to optimize the trajectory of the robot under the premise of satisfying the kinematic constraints, dynamic constraints an...
详细信息
ISBN:
(纸本)9798350344738;9798350344721
The trajectory optimization problem of cooperative six-axis robot based on time optimization is to optimize the trajectory of the robot under the premise of satisfying the kinematic constraints, dynamic constraints and task constraints of the robot, so that the time of movement in the working process is the shortest. After completing the kinematics solution of the six-axis cooperative robot, based on the 5-order B-spline interpolation trajectory, the particle swarm optimization algorithm is used to optimize the time interval between the trajectory nodes, and the particle swarm optimization algorithm is used to solve the robot trajectory with the lowest energy consumption. Finally, a suitable experiment is designed to prove the feasibility of the optimization scheme.
Pi Sigma artificial neural networks are a type of high-order neural network used in time series forecasting problems. In the Pi Sigma artificial neural networks, the weights between the hidden layer and the output lay...
详细信息
Pi Sigma artificial neural networks are a type of high-order neural network used in time series forecasting problems. In the Pi Sigma artificial neural networks, the weights between the hidden layer and the output layer are taken as constant and one, and the biases as constant and zero. Although this feature of the Pi Sigma artificial neural networks enables it to work with fewer parameters, it can also be seen as an obstacle to obtaining better forecasting performance. In this study, unlike classical Pi Sigma artificial neural networks, a modified Pi Sigma artificial neural network is proposed by taking the weights and biases as variables between the hidden layer and the output layer of the network. Thus, direct processing of the information coming to the output layer is prevented and the information coming to the output layer is weighted using different weights and bias values. The process of optimizing all the weights and bias values between the input and hidden layer, the hidden layer, and the output layer of the network is carried out together with the particleswarmoptimization method. The proposed modified Pi Sigma artificial neural networks are compared with some other artificial neural networks in the literature by analyzing much well-known time series. As a result of the applications, it is seen that the forecasting performance of the modified Pi Sigma artificial neural networks is better than both the classical Pi Sigma artificial neural networks and many other artificial neural networks.
暂无评论